Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2838 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.7613. Min Act: -0.0000

Data Index: 1257503 (C4 (Web Text))

Max Activating Token Index: 569

Text #1

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.5967. Min Act: -0.0000

Data Index: 414563 (C4 (Web Text))

Max Activating Token Index: 937

Text #2

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.5562. Min Act: -0.0001

Data Index: 1269298 (C4 (Web Text))

Max Activating Token Index: 702

Text #3

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.6326. Min Act: -0.0000

Data Index: 735140 (C4 (Web Text))

Max Activating Token Index: 862

Text #4

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.5612. Min Act: -0.0001

Data Index: 1063660 (C4 (Web Text))

Max Activating Token Index: 941

Text #5

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.5804. Min Act: -0.0001

Data Index: 1141940 (C4 (Web Text))

Max Activating Token Index: 997

Text #6

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.5933. Min Act: -0.0001

Data Index: 604097 (C4 (Web Text))

Max Activating Token Index: 223

Text #7

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.5805. Min Act: -0.0000

Data Index: 537321 (C4 (Web Text))

Max Activating Token Index: 834

Text #8

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.5627. Min Act: -0.0000

Data Index: 743509 (C4 (Web Text))

Max Activating Token Index: 136

Text #9

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.5558. Min Act: -0.0001

Data Index: 1042511 (C4 (Web Text))

Max Activating Token Index: 315

Text #10

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.5538. Min Act: -0.0001

Data Index: 1336765 (C4 (Web Text))

Max Activating Token Index: 873

Text #11

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.5293. Min Act: -0.0000

Data Index: 295637 (C4 (Web Text))

Max Activating Token Index: 85

Text #12

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.5761. Min Act: -0.0001

Data Index: 618442 (C4 (Web Text))

Max Activating Token Index: 959

Text #13

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.5114. Min Act: -0.0000

Data Index: 1068735 (C4 (Web Text))

Max Activating Token Index: 370

Text #14

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.5246. Min Act: -0.0000

Data Index: 1015705 (C4 (Web Text))

Max Activating Token Index: 1000

Text #15

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.5079. Min Act: -0.0000

Data Index: 1096495 (C4 (Web Text))

Max Activating Token Index: 999

Text #16

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.4691. Min Act: -0.0000

Data Index: 1169167 (C4 (Web Text))

Max Activating Token Index: 708

Text #17

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.5135. Min Act: -0.0000

Data Index: 935341 (C4 (Web Text))

Max Activating Token Index: 802

Text #18

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.4654. Min Act: -0.0000

Data Index: 975257 (C4 (Web Text))

Max Activating Token Index: 741

Text #19

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.4722. Min Act: -0.0000

Data Index: 868809 (C4 (Web Text))

Max Activating Token Index: 174